Deep Learning Based Biomedical NER Framework

Robert Phan, Thoai Man Luu, Rachel Davey, Girija Chetty

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

This paper describes a novel deep learning-based framework for biomedical name entity recognition. Bio-Entity name entity recognition task based on three different deep learning techniques: Feedforward Networks (FFNs), Recurrent Neural Networks (RNNs), and Hybrid Convolutional Neural Networks (CNNs), has allowed better latent feature learning and discovery for the complex NLP task. The performance evaluation of the proposed framework with the BioNLP dataset corresponding to biomedical entity recognition task, has led to promising performance, when assessed in terms of F-measure, Recall and Precision. The best performing deep learner based on Hybrid CNN approach has resulted in an F-score of 70.32%, and surpassed the performance reported by other participants in the Challenge task.
Original languageEnglish
Title of host publicationProceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018
EditorsSuresh Sundaram
Place of PublicationBangalore, India
PublisherIEEE
Pages33-40
Number of pages8
ISBN (Electronic)9781538692769
ISBN (Print)9781538692769
DOIs
Publication statusPublished - 18 Nov 2018
Event2018 Symposium Series on Computational Intelligence - Sheraton Grand Bangalore Hotel, Bengalore, India
Duration: 18 Nov 201821 Nov 2018
http://ieee-ssci2018.org/

Publication series

NameProceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018

Conference

Conference2018 Symposium Series on Computational Intelligence
Abbreviated titleIEEE-SSCI 2018
CountryIndia
CityBengalore
Period18/11/1821/11/18
Internet address

Cite this

Phan, R., Luu, T. M., Davey, R., & Chetty, G. (2018). Deep Learning Based Biomedical NER Framework. In S. Sundaram (Ed.), Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018 (pp. 33-40). [8628740] (Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018). Bangalore, India: IEEE. https://doi.org/10.1109/SSCI.2018.8628740
Phan, Robert ; Luu, Thoai Man ; Davey, Rachel ; Chetty, Girija. / Deep Learning Based Biomedical NER Framework. Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018. editor / Suresh Sundaram. Bangalore, India : IEEE, 2018. pp. 33-40 (Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018).
@inproceedings{ec8958121dd04f07966be12690b2c54a,
title = "Deep Learning Based Biomedical NER Framework",
abstract = "This paper describes a novel deep learning-based framework for biomedical name entity recognition. Bio-Entity name entity recognition task based on three different deep learning techniques: Feedforward Networks (FFNs), Recurrent Neural Networks (RNNs), and Hybrid Convolutional Neural Networks (CNNs), has allowed better latent feature learning and discovery for the complex NLP task. The performance evaluation of the proposed framework with the BioNLP dataset corresponding to biomedical entity recognition task, has led to promising performance, when assessed in terms of F-measure, Recall and Precision. The best performing deep learner based on Hybrid CNN approach has resulted in an F-score of 70.32{\%}, and surpassed the performance reported by other participants in the Challenge task.",
keywords = "convolutional neural networks, deep learning, feedforward networks, machine learning, optimization algorithm, recurrent neural networks",
author = "Robert Phan and Luu, {Thoai Man} and Rachel Davey and Girija Chetty",
year = "2018",
month = "11",
day = "18",
doi = "10.1109/SSCI.2018.8628740",
language = "English",
isbn = "9781538692769",
series = "Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018",
publisher = "IEEE",
pages = "33--40",
editor = "Suresh Sundaram",
booktitle = "Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018",

}

Phan, R, Luu, TM, Davey, R & Chetty, G 2018, Deep Learning Based Biomedical NER Framework. in S Sundaram (ed.), Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018., 8628740, Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018, IEEE, Bangalore, India, pp. 33-40, 2018 Symposium Series on Computational Intelligence, Bengalore, India, 18/11/18. https://doi.org/10.1109/SSCI.2018.8628740

Deep Learning Based Biomedical NER Framework. / Phan, Robert; Luu, Thoai Man; Davey, Rachel; Chetty, Girija.

Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018. ed. / Suresh Sundaram. Bangalore, India : IEEE, 2018. p. 33-40 8628740 (Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Deep Learning Based Biomedical NER Framework

AU - Phan, Robert

AU - Luu, Thoai Man

AU - Davey, Rachel

AU - Chetty, Girija

PY - 2018/11/18

Y1 - 2018/11/18

N2 - This paper describes a novel deep learning-based framework for biomedical name entity recognition. Bio-Entity name entity recognition task based on three different deep learning techniques: Feedforward Networks (FFNs), Recurrent Neural Networks (RNNs), and Hybrid Convolutional Neural Networks (CNNs), has allowed better latent feature learning and discovery for the complex NLP task. The performance evaluation of the proposed framework with the BioNLP dataset corresponding to biomedical entity recognition task, has led to promising performance, when assessed in terms of F-measure, Recall and Precision. The best performing deep learner based on Hybrid CNN approach has resulted in an F-score of 70.32%, and surpassed the performance reported by other participants in the Challenge task.

AB - This paper describes a novel deep learning-based framework for biomedical name entity recognition. Bio-Entity name entity recognition task based on three different deep learning techniques: Feedforward Networks (FFNs), Recurrent Neural Networks (RNNs), and Hybrid Convolutional Neural Networks (CNNs), has allowed better latent feature learning and discovery for the complex NLP task. The performance evaluation of the proposed framework with the BioNLP dataset corresponding to biomedical entity recognition task, has led to promising performance, when assessed in terms of F-measure, Recall and Precision. The best performing deep learner based on Hybrid CNN approach has resulted in an F-score of 70.32%, and surpassed the performance reported by other participants in the Challenge task.

KW - convolutional neural networks

KW - deep learning

KW - feedforward networks

KW - machine learning

KW - optimization algorithm

KW - recurrent neural networks

UR - http://www.scopus.com/inward/record.url?scp=85062791630&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/deep-learning-based-biomedical-ner-framework

U2 - 10.1109/SSCI.2018.8628740

DO - 10.1109/SSCI.2018.8628740

M3 - Conference contribution

SN - 9781538692769

T3 - Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018

SP - 33

EP - 40

BT - Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018

A2 - Sundaram, Suresh

PB - IEEE

CY - Bangalore, India

ER -

Phan R, Luu TM, Davey R, Chetty G. Deep Learning Based Biomedical NER Framework. In Sundaram S, editor, Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018. Bangalore, India: IEEE. 2018. p. 33-40. 8628740. (Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018). https://doi.org/10.1109/SSCI.2018.8628740